{"id":"https://openalex.org/W4416038742","doi":"https://doi.org/10.1109/iccv51701.2025.02036","title":"Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA","display_name":"Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416038742","doi":"https://doi.org/10.1109/iccv51701.2025.02036"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10225","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020817752","display_name":"Zhixuan Li","orcid":"https://orcid.org/0000-0001-7522-6678"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhixuan Li","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110228332","display_name":"Hyunse Yoon","orcid":"https://orcid.org/0009-0004-4423-8544"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunse Yoon","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082954314","display_name":"S.H. Lee","orcid":"https://orcid.org/0000-0001-6618-8489"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghoon Lee","raw_affiliation_strings":["Yonsei University,Department of Electrical and Electronic Engineering,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Electrical and Electronic Engineering,Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403129","display_name":"Weisi Lin","orcid":"https://orcid.org/0000-0001-9866-1947"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisi Lin","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21927","last_page":"21937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9416999816894531,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9416999816894531,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11904","display_name":"Spatial Cognition and Navigation","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/amodal-perception","display_name":"Amodal perception","score":0.9412000179290771},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6704000234603882},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6069999933242798},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5746999979019165},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5440999865531921},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.36160001158714294},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.32910001277923584}],"concepts":[{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.9412000179290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6870999932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683899998664856},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6704000234603882},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5440999865531921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C2777350023","wikidata":"https://www.wikidata.org/wiki/Q1154226","display_name":"Aura","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26570001244544983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10225","pdf_url":"https://arxiv.org/pdf/2503.10225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.10225","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10225","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10225","pdf_url":"https://arxiv.org/pdf/2503.10225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7363069556","display_name":null,"funder_award_id":"RS-2024-00398413","funder_id":"https://openalex.org/F4320323890","funder_display_name":"Korea Creative Content Agency"}],"funders":[{"id":"https://openalex.org/F4320323890","display_name":"Korea Creative Content Agency","ror":"https://ror.org/036vyg793"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Amodal":[0],"segmentation":[1,22,56],"aims":[2],"to":[3,27,36,63,91,151],"infer":[4],"the":[5,13,25,93,161],"complete":[6,94],"shape":[7,96],"of":[8,97],"occluded":[9,14,98],"objects,":[10],"even":[11],"when":[12],"region's":[15],"appearance":[16],"is":[17],"unavailable.":[18],"However,":[19],"current":[20],"amodal":[21,87,95],"methods":[23,46],"lack":[24],"capability":[26],"interact":[28],"with":[29,55,103,143],"users":[30],"through":[31],"text":[32,108],"input":[33],"and":[34,42,69,117,137,146],"struggle":[35],"understand":[37],"or":[38],"reason":[39],"about":[40],"implicit":[41],"complex":[43,74,153],"purposes.":[44],"While":[45],"like":[47],"LISA":[48],"integrate":[49],"multi-modal":[50],"large":[51],"language":[52],"models":[53],"(LLMs)":[54],"for":[57],"reasoning":[58,88],"tasks,":[59],"they":[60],"are":[61],"limited":[62],"predicting":[64],"only":[65],"visible":[66],"object":[67],"regions":[68],"face":[70],"challenges":[71],"in":[72],"handling":[73],"occlusion":[75],"scenarios.":[76],"To":[77],"address":[78],"these":[79],"limitations,":[80],"we":[81,132],"propose":[82],"a":[83,112,119,140],"novel":[84,141],"task":[85],"named":[86],"segmentation,":[89],"aiming":[90],"predict":[92],"objects":[99],"while":[100],"providing":[101],"answers":[102],"elaborations":[104],"based":[105],"on":[106,123,160],"user":[107],"input.":[109],"We":[110],"develop":[111],"generalizable":[113],"dataset":[114,121],"generation":[115],"pipeline":[116],"introduce":[118],"new":[120],"focusing":[122],"daily":[124],"life":[125],"scenarios,":[126],"encompassing":[127],"diverse":[128],"real-world":[129],"occlusions.":[130,154],"Furthermore,":[131],"present":[133],"AURA":[134],"(Amodal":[135],"Understanding":[136],"Reasoning":[138],"Assistant),":[139],"model":[142],"advanced":[144],"global":[145],"spatial-level":[147],"designs":[148],"specifically":[149],"tailored":[150],"handle":[152],"Extensive":[155],"experiments":[156],"validate":[157],"AURA's":[158],"effectiveness":[159],"proposed":[162],"dataset.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}